October AMP_Digital

A D V A N C E D M A T E R I A L S & P R O C E S S E S | O C T O B E R 2 0 1 8 2 5 desired results using plain mathemat- ics [11] . Such mathematical tools in Lu- met systems even enable improving existing recipes. Existing recipes are usually not op- timal from the customer’s point of view. For example, consider a unit that pro- duces pipes in only three diameters, expecting the customer to select one of the three irrespective of actual re- quirements. Also, there is often “over quality” in terms of some product prop- erties, which unnecessarily increases product cost. Nonlinear models of rel- evant variables in combination with appropriate mathematical tools help tailor-make products with minimal ex- perimental effort, thereby increasing competitiveness. An example is shown in Fig. 7. With the same constraints as Fig. 6, minimiz- ing production cost per unit volume is also specified. Considering some of the existing recipes at NMC Termonova and optimizing them for production cost shows that in some cases, cost could be reduced by several percent. ~AM&P For more information: Abhay Bulsari, Nonlinear Solutions Oy, Kaivokatu 10A 21, 20520 Turku, Finland, +358.2.2154721, abulsari@abo.fi, www. nonlinear-solutions-oy.com. References 1. K. Hornik, M. Stinchcombe, and H. White, Multilayer Feedforward Net- works are Universal Approximators, Neural Networks, Vol 2, p 359-366, 1989. 2. A. Bulsari (ed.), Neural Networks for Chemical Engineers, Elsevier, 1995. 3. A. Bulsari, P. Pitkänen, and B. Malm, Nonlinear Modelling Paves the Way to Bespoke Polymers, British Plastics and Rubber, p 4-5, Dec. 2002. 4. A. Bulsari, et al., Nonlinear Models of Mechanical Properties Reduce Rub- ber Recipe Development Time, Rubber World, Vol 252, No. 6, p 28-33, Sept. 2015. 5. A. Bulsari, et al., Nonlinear Models Help Cement Process and Product Development, Global Cement Magazine, p 24-28, Nov. 2016. 6. A. Bulsari, H. Kylmämetsä, and K. Juvas, Nonlinear Models of Workability and Compressive Strength Help Minimize Costs, Concrete Plant Intl., No. 6, p 36-42, Dec. 2009. 7. A. Bulsari, H. Keife, and J. Geluk, Nonlinear Models Provide Better Con- trol of Annealed Brass Strip Micro- structure, Adv. Matls. and Proc. , Vol 170, p 18-20, July 2012. 8. A. Bulsari, I. Vuoristo, and I. Kop- pinen, Nonlinear Models Tune Precip- itation Hardening, Adv. Matls. and Proc., Vol 168, No. 5, p 31-33, May 2010. 9. A. Bulsari, et al., Models Add Efficiency to Bioabsorbable Implant Development, Medical Design Technol., Vol 19, No. 2, p 26-28, March 2015. 10. A. Bulsari, et al., Correlation of In Vitro and In Vivo Dissolution Behavior of Stonewools Using Nonlinear Modelling Techniques, J. European Ceram. Soc., Vol 27, No. 2-3, p 1837-1841, 2007. 11. P. E. Gill,W. Murray, andM. H.Wright, Practical Optimization , Academic Press, London, 1981. Fig. 7 — Optimization calculation that minimizes production cost per unit volume taking into account customer requirements.